mlx-community/Dolphin-2.9.3-Mistral-Nemo-12b-4bit

Quantization vs mistralai/Mistral-Nemo-Base-2407. mlx-community/Dolphin-2.9.3-Mistral-Nemo-12b-4bit is a quantized version of the other (U32/F16).

On the Hub · Downloads on Model Pulse